Voice control method and system adaptive to user historical behaviors, electronic equipment and storage medium

Abstract

The invention provides a voice control method and system adaptive to user historical behaviors, electronic equipment and a storage medium, and the method comprises the following steps: to-be-controlled equipment collects a control audio signal outputted by a user in an external environment and environment data of the external environment in real time, the to-be-controlled equipment locally analyzes the control audio signal, and the environment data of the external environment is transmitted to the to-be-controlled equipment; extracting and recording a control instruction and an association instruction recorded in the control audio signal; the to-be-controlled device executes a target action based on the control instruction, and performs connection analysis on the control instruction related to the current control audio signal, the association instruction and the environment data to generate a data set and store the data set; and when the to-be-controlled equipment acquires the associated instruction or the environment data recorded in the stored data set at the future moment, the to-be-controlled equipment actively executes a target action referred to by a control instruction corresponding to the associated instruction or the environment data.

Description

Technical Field

[0001] The present invention belongs to the field of voice control technology, and in particular relates to a voice control method, system, electronic device and storage medium adapted to user historical behavior. Background Art

[0002] Voice control refers to a technology that uses human voice commands to operate or interact with devices and systems. Using voice control technology, users can make the controlled devices perform various tasks by speaking specific commands, such as controlling smart home devices to perform various target actions.

[0003] Under existing technologies, due to the diverse design of application scenarios, most devices to be controlled use an online network method to achieve voice recognition and control, so a network module must be added to the system, increasing product costs; and in the absence of a network, such as arrears or network disconnection, the devices to be controlled cannot be used normally; at the same time, the online mode requires all audio data in the current environment to be transmitted to the server via the network, which is bound to greatly increase the risk of user privacy leakage; if the devices to be controlled use an offline method, the functions that can generally be realized by the devices to be controlled are relatively simple, and they can only simply control the operation of the device in an inherent way, and cannot make real-time and proactive intelligent adjustments based on user usage habits. Summary of the Invention

[0004] The present invention aims to provide a voice control method, system, electronic device and storage medium that are adapted to user historical behavior, so as to solve the technical problem that conventional voice control methods and systems in the existing technology cannot be combined with user historical behavior to achieve intelligent and autonomous control if they are adopted in an offline manner.

[0005] To solve the above problems, the technical solution of the present invention is: a voice control method adapted to the user's historical behavior, applied to a voice control system in offline mode to realize behavior control of a number of local controlled devices, comprising the following steps: S1: The device to be controlled collects the control audio signal output by the user in the external environment and the environmental data of the external environment in real time; The device to be controlled locally analyzes the control audio signal, extracts and records the control instructions and associated instructions recorded in the control audio signal; S2: The controlled device executes the target action based on the control instruction, and connects and analyzes the control instruction, associated instruction and environmental data related to the current control audio signal, generates a data set and stores it together; S3: When the device to be controlled collects the associated instruction or environmental data recorded in the stored data set at a future time, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the associated instruction or environmental data.

[0006] Preferably, a wake-up word is pre-recorded in the device to be controlled. In S1, the device to be controlled collects a control audio signal output by a user in an external environment in real time, specifically comprising the following steps: S11: The controlled device collects a wake-up audio signal output by the user in the external environment in real time. If a wake-up word is recognized, the controlled device enters a wake-up state from a sleep state and maintains a fixed wake-up duration; In the wake-up state, if the controlled device collects a control audio signal, the wake-up time is reset and the control audio signal continues to be collected. If the controlled device does not collect a new set of control audio signals within the wake-up time, the controlled device re-enters the sleep state.

[0007] Preferably, the target action executed by the device to be controlled is set to regulate the environmental state of the external environment in which the device to be controlled is located; The environmental data related to the current control audio signal refers to the environmental data collected at the same time as the control audio signal. The environmental data includes the temperature parameters, humidity parameters, air pressure parameters, wind speed and direction parameters, time parameters, light intensity parameters, color temperature parameters, noise parameters or gas content parameters of the external environment in which the controlled device is currently located.

[0008] Preferably, it is set that in the same or adjacent control audio signals, the associated instruction refers to the environmental perception and feedback expression associated with the control instruction; The associated instructions include environmental perception and feedback expression of temperature parameters, humidity parameters, air pressure parameters, wind speed and direction parameters, time parameters, light intensity parameters, color temperature parameters, noise parameters or gas content parameters of the external environment in which the controlled device is currently located.

[0009] Preferably, in S3, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the associated instruction, which specifically includes the following steps: S31: The controlled device collects a control audio signal output by a user in an external environment in real time. When only a second associated instruction is extracted from the control audio signal, the second associated instruction is compared with a plurality of first associated instructions stored in the data set. If any first associated instruction matches the second associated instruction, the first control instruction linked to the current first associated instruction is called. The device to be controlled inquires the user whether to execute the target action according to the first control instruction. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

[0010] Preferably, in S3, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the environmental data, which specifically includes the following steps: S32: The controlled device collects second environmental data of the external environment in real time, compares the second environmental data with a plurality of first environmental data stored in the data set, and calls a first control instruction associated with the current first environmental data if any of the first environmental data matches the second environmental data; The device to be controlled inquires the user whether to execute the target action according to the first control instruction. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

[0011] Preferably, a voice control method adapted to a user's historical behavior further includes the following steps: S4: The controlled device collects a control audio signal output by a user in an external environment in real time, extracts a primary control instruction from the control audio signal, and performs a primary target action based on the primary control instruction. The primary target action includes starting and stopping the controlled device. The controlled device collects second environmental data of the external environment in real time, compares the second environmental data with a plurality of first environmental data stored in the data set, and calls a secondary control instruction linked to the current first environmental data if any of the first environmental data matches the second environmental data; The device to be controlled asks the user whether to further perform the target action according to the secondary control instruction. If the user confirms, the device to be controlled performs the target action based on the secondary control instruction. The secondary target action includes the action of adjusting the environmental parameters of the external environment by the device to be controlled.

[0012] Based on the same concept, the present invention also provides a voice control system adapted to a user's historical behavior, which is used to execute a voice control method adapted to a user's historical behavior as described in any one of the above, comprising: an acquisition module, configured to acquire a control audio signal output by a user in an external environment through a microphone device, and to acquire environmental data in an external environment through a sensor device; A processing module is used to analyze the control audio signal in an offline mode, extract the control instructions and related instructions recorded in the control audio signal, and connect the relevant control instructions, related instructions and environmental data for processing; The execution module is used to enable the device to be controlled to execute the target action based on the control instruction, and to enable the device to be controlled to actively execute the target action indicated by the control instruction corresponding to the associated instruction or environmental data based on the associated instruction or environmental data.

[0013] Based on the same concept, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement any one of the above-mentioned voice control methods adapted to user historical behavior.

[0014] Based on the same concept, the present invention also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the above-mentioned voice control methods adapted to user historical behavior.

[0015] Due to the adoption of the above technical solution, the present invention has the following advantages and positive effects compared with the prior art: The present invention provides a voice control method, system, electronic device, and storage medium that adapt to a user's historical behavior. The controlled device is used in offline mode, effectively reducing the risk of user privacy leakage. During the voice control process of the controlled device, in addition to collecting the control instructions provided by the user, associated instructions and environmental data associated with the control instructions can also be collected. The data set of the control instructions, associated instructions, and environmental data is saved as the user's usage habits. When the controlled device subsequently collects associated instructions or environmental data, it can actively execute the target action indicated by the control instruction corresponding to the associated instruction or environmental data by inferring the user's usage habits, thereby realizing the autonomous control function of the controlled device to adapt to the user's historical behavior and improving the intelligence and control efficiency of the controlled device. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a voice control method adapted to user historical behavior provided by the present invention; Figure 2 A schematic structural diagram of a voice control system adapted to user historical behavior provided by the present invention. DETAILED DESCRIPTION

[0017] The following is a detailed description of a method, system, electronic device, and storage medium for voice control adapted to user history behavior proposed by the present invention, in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and claims.

[0018] First embodiment See Figure 1-Figure 2 This embodiment provides a voice control method adapted to the user's historical behavior, which is applied to the control system to implement behavior control of several local controlled devices in offline mode, so that the controlled devices can realize intelligent autonomous control functions of the controlled devices according to the user's historical behavior.

[0019] A voice control method adapted to user historical behavior includes the following steps: S1: The device to be controlled collects the control audio signal output by the user in the external environment and the environmental data of the external environment in real time.

[0020] The control audio signal refers to an audio signal containing a control command for the device to be controlled.

[0021] The device to be controlled analyzes the control audio signal locally, extracts and records the control instructions and associated instructions recorded in the control audio signal.

[0022] Taking an air conditioner as an example of a controlled device, the control instruction in this embodiment refers to a user's direct control command over the operating state of the controlled device. The associated instruction refers to the environmental perception and feedback expression associated with the control instruction. For example, when the user outputs a control audio signal such as "Turn on the air conditioner for me! It's too hot" or "It's too stuffy in the room! Turn on the air conditioner," "Turn on the air conditioner" is a control instruction. The controlled device has pre-stored local control vocabulary for controlling the device's operating state, such as "Turn on the air conditioner," "Turn off the air conditioner," and "Adjust the air conditioner temperature to XX degrees Celsius." Local search allows for the corresponding control instruction to be identified. "It's too hot" or "It's too stuffy in the room" are associated instructions. Because it's too hot or too stuffy, the controlled device needs to turn on the air conditioner. Therefore, there is a clear causal relationship between the associated instruction and the control instruction.

[0023] S2: The device to be controlled executes the target action based on the control instruction, and connects and analyzes the control instruction, associated instruction and environmental data related to the current control audio signal, generates a data set and merges and saves it.

[0024] Taking the air conditioner as an example of a device to be controlled, when the control audio signal output by the user is "Help me turn on the air conditioner, it's too hot" or "It's too stuffy in the room, turn on the air conditioner", the device to be controlled executes the target action of turning on the air conditioner. At the same time, it connects and analyzes the associated instructions such as "It's too hot" or "It's too stuffy in the room", the control instruction of "Turn on the air conditioner", and the environmental data such as the temperature and humidity of the external environment at this time, that is, establishes a data set of control instructions-associated instructions-environmental data, and the data set is used to infer the user's usage habits for the air conditioner.

[0025] S3: When the device to be controlled collects the associated instruction or environmental data recorded in the stored data set at a future time, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the associated instruction or environmental data.

[0026] Still taking the air conditioner as an example of a device to be controlled, in the future, when the device to be controlled collects the control audio signal output by the user and the content is only related instructions such as "it's too hot" or "it's too stuffy indoors", or collects environmental data such as the temperature and humidity of the external environment, which are consistent or similar to the related instructions or environmental data recorded in the stored data set, by matching the user's historical behavior, the device to be controlled actively executes the target action referred to by the control instruction corresponding to the current related instruction or environmental data in the data set, that is, actively executes the target action of turning on the air conditioner.

[0027] It is worth noting that the learning and understanding of the user's historical behavior by the device to be controlled is a process behavior. For example, during the active voice control process, the user repeatedly associates and outputs related commands such as "it's too hot" or "it's too stuffy indoors" with the control command "turn on the air conditioner", or when the device to be controlled actively executes the target action indicated by the control command corresponding to the associated command or environmental data, and the user approves of the prediction result, it will strengthen the device to be controlled's understanding of the correlation between the control command, associated command and environmental data, and through continuous reinforcement learning, improve the accuracy of the device to be controlled in predicting user behavior.

[0028] In summary, this embodiment provides a voice control method that adapts to the user's historical behavior. When the device to be controlled is offline, it learns the user's usage habits by collecting control instructions, associated instructions and environmental data related to the control audio signal, and realizes the intelligent autonomous control function of the device to be controlled based on the user's historical behavior during the subsequent use of the device to be controlled.

[0029] The following further details the specific steps and functions of the voice control method adapted to the user's historical behavior provided by this embodiment: Preferably, in one embodiment, a wake-up word is pre-recorded in the device to be controlled. In S1, the device to be controlled collects a control audio signal output by a user in an external environment in real time, specifically comprising the following steps: S11: The controlled device collects the wake-up audio signal output by the user in the external environment in real time. If the wake-up word is recognized, the controlled device enters the wake-up state from the sleep state and maintains the wake-up time for a fixed period of time; In the wake-up state, if the controlled device collects a control audio signal, the wake-up time is reset and the control audio signal continues to be collected. If the controlled device does not collect a new set of control audio signals within the wake-up time, the controlled device re-enters the sleep state.

[0030] Take an air conditioner as an example of a device to be controlled. The wake-up word pre-recorded in the device to be controlled is "Hello, air conditioner". During the voice control process of the device to be controlled, the device to be controlled is first in a dormant state and only monitors and identifies whether the wake-up word exists in the audio signal output by the user. If the wake-up word does not exist in the audio signal, the device to be controlled remains in a dormant state. If the wake-up word exists in the audio signal, the device to be controlled enters a wake-up state from the dormant state, and the audio signal containing the wake-up word is the wake-up audio signal. The wake-up state of the device to be controlled can maintain a fixed wake-up duration. For example, taking 10 seconds as an example, during the 10-second countdown, the device to be controlled can collect the control audio signal output by the user in the external environment. Every time a new set of control audio signals is collected, the wake-up duration is reset until the 10-second countdown returns to zero within a single wake-up duration. If a new set of control audio signals is still not collected, it proves that the user has completed the complete output of the relevant control command, and the device to be controlled re-enters the dormant state.

[0031] It is worth noting that the dormant state and awake state of the controlled device in this embodiment only refer to the audio signal collection function of the controlled device for the external environment, and have nothing to do with the environment adjustment function of the controlled device itself.

[0032] Through this embodiment, only when the controlled device recognizes the wake-up word will the audio signal output by the user be deeply collected and processed, reducing the possibility of unnecessary voice data being collected and transmitted, thereby enhancing the user's privacy and security, and avoiding false triggering of the controlled device due to environmental noise or other non-command sounds, thereby improving the stability of voice control of the controlled device.

[0033] Preferably, in one embodiment, the target action executed by the device to be controlled is set to regulate the environmental state of the external environment in which the device to be controlled is located.

[0034] In S1 , when the device to be controlled collects the control audio signal output by the user in the external environment and the environmental data of the external environment in real time, the control audio signal and the environmental data collected at the same time maintain a corresponding relationship.

[0035] That is, the environmental data related to the current control audio signal refers to the environmental data collected at the same time as the control audio signal. The environmental data includes temperature parameters, humidity parameters, air pressure parameters, wind speed and direction parameters, time parameters, light intensity parameters, color temperature parameters, noise parameters or gas content parameters of the external environment in which the controlled device is currently located.

[0036] It is worth noting that the above-mentioned environmental data refer to the environmental adjustment parameters that can be realized in different devices to be controlled. For example, the smart air conditioner is configured to adjust the temperature parameters, humidity parameters, wind speed and wind direction parameters in the external environment, and the smart lamps are configured to adjust the light intensity parameters, color temperature parameters, etc. in the external environment. Different environmental data collection needs to be selected according to the actual type of device to be controlled.

[0037] Preferably, in one embodiment, it is set that in the same or adjacent control audio signal, the associated instruction refers to the environmental perception and feedback expression associated with the control instruction.

[0038] The associated instructions include environmental perception and feedback expression of temperature parameters, humidity parameters, air pressure parameters, wind speed and direction parameters, time parameters, light intensity parameters, color temperature parameters, noise parameters or gas content parameters of the external environment in which the controlled device is currently located.

[0039] Taking an air conditioner as an example of a device to be controlled, the associated instruction of "too hot" is used to indicate that the temperature parameter of the external environment of the device to be controlled is too high.

[0040] Preferably, in one embodiment, in S3, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the associated instruction, specifically including the following steps: S31: The controlled device collects a control audio signal output by a user in an external environment in real time. When only a second associated instruction is extracted from the control audio signal, the second associated instruction is compared with a plurality of first associated instructions stored in the data set. If any first associated instruction matches the second associated instruction, the first control instruction linked to the current first associated instruction is called. The device to be controlled asks the user whether to execute the target action according to the first control instruction. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

[0041] Specifically, taking an air conditioner as an example of a device to be controlled, the device to be controlled collects a control audio signal output by the user, and the control audio signal contains a second associated instruction "I feel a little hot". At this time, a data set about "Turn on the air conditioner - it's too hot" has been stored locally in the device to be controlled. The second associated instruction ("I feel a little hot") is compared with the first associated instruction ("it's too hot"). The environmental perception and feedback expressed by the two are similar, so the first control instruction ("turn on the air conditioner") linked to the current first associated instruction is called.

[0042] The controlled device can ask the user via voice or screen visualization whether they agree to turn on the air conditioner. If the user confirms, the controlled device executes the target action based on the first control instruction. During this process, the user's choice will further influence the controlled device's learning and understanding of the user's usage habits. That is, if the user agrees with the controlled device's prediction result, it proves that the controlled device's prediction is successful, and the controlled device will increase the weight of the current prediction choice in subsequent prediction model training. Conversely, if the user disagrees with the controlled device's prediction result, it proves that the controlled device's prediction is a failure, and the controlled device will reduce the weight of the current prediction choice in subsequent prediction model training.

[0043] Preferably, in one embodiment, in S3, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the environmental data, specifically comprising the following steps: S32: The controlled device collects second environmental data of the external environment in real time, compares the second environmental data with a plurality of first environmental data stored in the data set, and calls a first control instruction associated with the current first environmental data if any of the first environmental data matches the second environmental data; The device to be controlled asks the user whether to execute the target action according to the first control instruction. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

[0044] Specifically, taking the air conditioner as an example of a device to be controlled, even if the user does not output any control audio signal, the device to be controlled will still collect the second environmental data of the external environment in real time (such as the external environmental temperature is 28°C). At this time, a data set about "turn on the air conditioner - the external environmental temperature before turning on the air conditioner" has been stored locally in the device to be controlled. That is, in the user's historical behavior, when the external environmental temperature reaches 26°C, the user may choose to turn on the air conditioner, so the second environmental data (the external environmental temperature is 28°C) is compared with the first environmental data (the external environmental temperature is 26°C before turning on the air conditioner), indicating that the external environmental temperature is too high at this time, so the first control instruction ("turn on the air conditioner") linked to the current first environmental data is called.

[0045] Similarly, the device to be controlled can ask the user whether to agree to turn on the air conditioner through voice or screen visualization display. If the user confirms, the device to be controlled performs the target action based on the first control instruction.

[0046] Preferably, in one embodiment, a voice control method adapted to a user's historical behavior further includes the following steps: S4: The controlled device collects the control audio signal output by the user in the external environment in real time, extracts the first-level control instruction from the control audio signal, and executes the first-level target action based on the first-level control instruction. The first-level target action includes starting and stopping the controlled device. The controlled device collects the second environment data of the external environment in real time, compares the second environment data with a plurality of first environment data stored in the data set, and calls the secondary control instruction linked to the current first environment data if any of the first environment data matches the second environment data; The device to be controlled asks the user whether to further perform the target action according to the secondary control instruction. If the user confirms, the device to be controlled performs the target action based on the secondary control instruction. The secondary target action includes the action of adjusting the environmental parameters of the external environment by the device to be controlled.

[0047] In this embodiment, the control instructions provided by the user include first-level control instructions and second-level control instructions. The first-level control instructions refer to the start and stop control of the controlled device, and the second-level control instructions refer to further adjustment of the environmental adjustment function of the controlled device under the premise that the controlled device is started, such as adjusting the temperature of the air conditioner, the brightness of the lamp, etc.

[0048] That is, during voice control of the air conditioner, the controlled device, while in a stopped state, first collects the control audio signal output by the user. This control audio signal contains a primary control command ("turn on the air conditioner"). Based on this primary control command, the controlled device executes the primary target action ("turn on the air conditioner"). At this point, the controlled device actively collects the second environmental data of the external environment (the external ambient temperature is 26°C). The controlled device also has a local data set for "Lower the air conditioner temperature by 2°C - external ambient temperature is 26°C." This means that in the user's historical behavior, when the external ambient temperature reaches 26°C, the user prefers to lower the air conditioner temperature by another 2°C. Therefore, the controlled device invokes the first control command ("Lower the air conditioner temperature by 2°C") associated with the current first environmental data (the external ambient temperature is 26°C).

[0049] Finally, the device to be controlled may ask the user whether to agree to adjust the temperature of the air conditioner through voice or screen visualization. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

[0050] It can be seen from this that in this embodiment, the voice control method adapted to the user's historical behavior also includes segmented control, which includes both start and stop control of the controlled device and automatic adjustment control of the specific environmental adjustment parameters of the controlled device after startup, further optimizing the fluency and intelligence of the controlled device during the voice control process.

[0051] Second embodiment Based on the same idea, see Figure 2 The present invention further provides a voice control system adapted to user historical behavior, which is used to execute a voice control method adapted to user historical behavior as described in any one of the first embodiments, including: The acquisition module is used to acquire the control audio signal output by the user in the external environment through the microphone device, and to acquire the environmental data in the external environment through the sensor device.

[0052] The processing module is used to analyze the control audio signal in an offline mode, extract the control instructions and associated instructions recorded in the control audio signal, and connect the relevant control instructions, associated instructions and environmental data for processing.

[0053] The execution module is used to enable the device to be controlled to execute the target action based on the control instruction, and to enable the device to be controlled to actively execute the target action indicated by the control instruction corresponding to the associated instruction or environmental data based on the associated instruction or environmental data.

[0054] The functional implementation of each component unit in the above voice control system corresponds to each step in the above voice control method embodiment, and their functions and implementation processes will not be repeated here one by one.

[0055] This embodiment further provides an electronic device, including a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement the above-mentioned voice control method. The electronic device can be a server or a terminal device.

[0056] This embodiment also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the steps of the above-mentioned voice control method.

[0057] In summary, the present invention provides a voice control method, system, electronic device and storage medium that adapt to the user's historical behavior. The device to be controlled is used in offline mode, which effectively reduces the risk of user privacy leakage. During the voice control process of the device to be controlled, in addition to collecting the control instructions provided by the user, the associated instructions and environmental data associated with the control instructions can also be collected, and the data set of the control instructions, associated instructions and environmental data is saved as the user's usage habits. When the device to be controlled subsequently collects the associated instructions or environmental data, it can actively execute the target action indicated by the control instruction corresponding to the associated instruction or environmental data by inferring the user's usage habits, thereby realizing the autonomous control function of the device to be controlled to adapt to the user's historical behavior and improving the intelligence and control efficiency of the device to be controlled.

[0058] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments. Even if various changes are made to the present invention, if these changes fall within the scope of the claims of the present invention and their equivalents, they still fall within the scope of protection of the present invention.

Claims

1. A voice control method adapted to user historical behavior, characterized in that: Applied to the voice control system to implement behavior control of several local controlled devices in offline mode, including the following steps: S1: The device to be controlled collects the control audio signal output by the user in the external environment and the environmental data of the external environment in real time; The device to be controlled locally analyzes the control audio signal, extracts and records the control instructions and associated instructions recorded in the control audio signal; S2: The controlled device executes the target action based on the control instruction, and connects and analyzes the control instruction, associated instruction and environmental data related to the current control audio signal, generates a data set and stores it together; S3: When the device to be controlled collects the associated instruction or environmental data recorded in the stored data set at a future time, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the associated instruction or environmental data.

2. The voice control method adapted to user historical behavior according to claim 1, characterized in that: The device to be controlled has a wake-up word pre-recorded in it. In S1, the device to be controlled collects a control audio signal output by a user in an external environment in real time, specifically including the following steps: S11: The controlled device collects a wake-up audio signal output by the user in the external environment in real time. If a wake-up word is recognized, the controlled device enters a wake-up state from a sleep state and maintains a fixed wake-up duration; In the wake-up state, if the controlled device collects a control audio signal, the wake-up time is reset and the control audio signal continues to be collected. If the controlled device does not collect a new set of control audio signals within the wake-up time, the controlled device re-enters the sleep state.

3. The voice control method adapted to user historical behavior according to claim 1, characterized in that: Setting a target action to be executed by the device to be controlled to regulate the environmental state of the external environment in which the device to be controlled is located; The environmental data related to the current control audio signal refers to the environmental data collected at the same time as the control audio signal. The environmental data includes the temperature parameters, humidity parameters, air pressure parameters, wind speed and direction parameters, time parameters, light intensity parameters, color temperature parameters, noise parameters or gas content parameters of the external environment in which the controlled device is currently located.

4. The voice control method adapted to user historical behavior according to claim 3, characterized in that: Set in the same or adjacent control audio signal, the associated instruction refers to the environmental perception and feedback expression associated with the control instruction; The associated instructions include environmental perception and feedback expression of temperature parameters, humidity parameters, air pressure parameters, wind speed and direction parameters, time parameters, light intensity parameters, color temperature parameters, noise parameters or gas content parameters of the external environment in which the controlled device is currently located.

5. The voice control method adapted to user historical behavior according to claim 1, characterized in that: In S3, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the associated instruction, which specifically includes the following steps: S31: The controlled device collects a control audio signal output by a user in an external environment in real time. When only a second associated instruction is extracted from the control audio signal, the second associated instruction is compared with a plurality of first associated instructions stored in the data set. If any first associated instruction matches the second associated instruction, the first control instruction linked to the current first associated instruction is called. The device to be controlled inquires the user whether to execute the target action according to the first control instruction. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

6. The voice control method adapted to user historical behavior according to claim 5, characterized in that: In S3, the device to be controlled actively executes the target action indicated by the control instruction corresponding to the environmental data, which specifically includes the following steps: S32: The controlled device collects second environmental data of the external environment in real time, compares the second environmental data with a plurality of first environmental data stored in the data set, and calls a first control instruction associated with the current first environmental data if any of the first environmental data matches the second environmental data; The device to be controlled inquires the user whether to execute the target action according to the first control instruction. If the user confirms, the device to be controlled executes the target action based on the first control instruction.

7. The voice control method adapted to user historical behavior according to claim 1, characterized in that: The following steps are also included: S4: The controlled device collects a control audio signal output by a user in an external environment in real time, extracts a primary control instruction from the control audio signal, and performs a primary target action based on the primary control instruction. The primary target action includes starting and stopping the controlled device. The controlled device collects second environmental data of the external environment in real time, compares the second environmental data with a plurality of first environmental data stored in the data set, and calls a secondary control instruction linked to the current first environmental data if any of the first environmental data matches the second environmental data; The device to be controlled asks the user whether to further perform the target action according to the secondary control instruction. If the user confirms, the device to be controlled performs the target action based on the secondary control instruction. The secondary target action includes the action of adjusting the environmental parameters of the external environment by the device to be controlled.

8. A voice control system adapted to user historical behavior, characterized in that: A method for performing a voice control method adapted to a user's historical behavior according to any one of claims 1 to 7, comprising: an acquisition module, configured to acquire a control audio signal output by a user in an external environment through a microphone device, and to acquire environmental data in an external environment through a sensor device; A processing module is used to analyze the control audio signal in an offline mode, extract the control instructions and related instructions recorded in the control audio signal, and connect the relevant control instructions, related instructions and environmental data for processing; The execution module is used to enable the device to be controlled to execute the target action based on the control instruction, and to enable the device to be controlled to actively execute the target action indicated by the control instruction corresponding to the associated instruction or environmental data based on the associated instruction or environmental data.

9. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the voice control method adapted to the user's historical behavior as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to implement the voice control method adapted to user historical behavior as described in any one of claims 1-8.

Images